s-a-barnett

PrioritizedSR

Code for 'PARSR: Priority-Adjusted Replay for Successor Representations' by Barnett and Momennejad (2022).

academic-kickstart

bayesian-persuasion

Code accompanying the paper: Barnett, S.A., Griffiths, T.L., & Hawkins, R.D. (2022). A pragmatic account of the weak evidence effect. Open Mind.

deep-successor-features-for-transfer

A reusable framework for successor features for transfer in deep reinforcement learning using keras.

man-opt

588 Project 1: Optimization on smooth manifolds for low-rank matrix completion

Melting-Pot-Contest-2023

multinomial-classes

This is an implementation of two different classes of multinomials: commutative and non-commutative. This is able to add and multiply polynomials, and evaluate them at a point in R^d.

PettingZoo

An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities